A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network
arXiv:1712.02121 · doi:10.18653/v1/N18-2053
Abstract
In this paper, we propose a novel embedding model, named ConvKB, for knowledge base completion. Our model ConvKB advances state-of-the-art models by employing a convolutional neural network, so that it can capture global relationships and transitional characteristics between entities and relations in knowledge bases. In ConvKB, each triple (head entity, relation, tail entity) is represented as a 3-column matrix where each column vector represents a triple element. This 3-column matrix is then fed to a convolution layer where multiple filters are operated on the matrix to generate different feature maps. These feature maps are then concatenated into a single feature vector representing the input triple. The feature vector is multiplied with a weight vector via a dot product to return a score. This score is then used to predict whether the triple is valid or not. Experiments show that ConvKB achieves better link prediction performance than previous state-of-the-art embedding models on two benchmark datasets WN18RR and FB15k-237.
In Proceedings of NAACL-HLT 2018, to appear
References in corpus (4)
Cited by in corpus (74)
- A Survey on Knowledge Graphs: Representation, Acquisition and Applications
- KG-BERT: BERT for Knowledge Graph Completion
- Quaternion Knowledge Graph Embeddings
- A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
- Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion
- Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework
- IMF: Interactive Multimodal Fusion Model for Link Prediction
- A Review of Knowledge Graph Completion
- TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
- CoKE: Contextualized Knowledge Graph Embedding
- Integrating Graph Contextualized Knowledge into Pre-trained Language Models
- Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion
- The Survey on Multi-Source Data Fusion in Cyber-Physical-Social Systems:Foundational Infrastructure for Industrial Metaverses and Industries 5.0
- Graph Collaborative Reasoning
- Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs
- Medical Entity Disambiguation Using Graph Neural Networks
- Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
- Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
- HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion
- A Survey on Graph Neural Networks for Knowledge Graph Completion
- A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
- r-GAT: Relational Graph Attention Network for Multi-Relational Graphs
- Triple Classification for Scholarly Knowledge Graph Completion
- Knowledge-based Entity Prediction for Improved Machine Perception in Autonomous Systems
- Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning
- Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding
- Composing Knowledge Graph Embeddings via Word Embeddings
- Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion
- Modeling relation paths for knowledge base completion via joint adversarial training
- Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning
- Knowledge Graph Embedding using Graph Convolutional Networks with Relation-Aware Attention
- KGClean: An Embedding Powered Knowledge Graph Cleaning Framework
- Knowledge Base Completion: Baseline strikes back (Again)
- A Re-evaluation of Knowledge Graph Completion Methods
- Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction
- BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining
- Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph
- Discrete Knowledge Graph Embedding based on Discrete Optimization
- WikiDataSets: Standardized sub-graphs from Wikidata
- DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion
- Drug-Drug Interaction Prediction with Wasserstein Adversarial Autoencoder-based Knowledge Graph Embeddings
- Out-of-Vocabulary Entities in Link Prediction
- Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
- Reviving the Context: Camera Trap Species Classification as Link Prediction on Multimodal Knowledge Graphs
- KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization and Completion
- NASE: Learning Knowledge Graph Embedding for Link Prediction via Neural Architecture Search
- TransEdge: Translating Relation-contextualized Embeddings for Knowledge Graphs
- Disentangle-based Continual Graph Representation Learning
- Drug Similarity and Link Prediction Using Graph Embeddings on Medical Knowledge Graphs
- Prediction of Adverse Biological Effects of Chemicals Using Knowledge Graph Embeddings
- Convolutional Hypercomplex Embeddings for Link Prediction
- PPKE: Knowledge Representation Learning by Path-based Pre-training
- Neural Consciousness Flow
- Capturing and Anticipating User Intents in Data Analytics via Knowledge Graphs
- Learning Structured Embeddings of Knowledge Graphs with Adversarial Learning Framework
- Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion
- Towards Building a Multilingual Sememe Knowledge Base: Predicting Sememes for BabelNet Synsets
- DisenE: Disentangling Knowledge Graph Embeddings
- A Systematic Investigation of KB-Text Embedding Alignment at Scale
- A Temporal Knowledge Graph Completion Method Based on Balanced Timestamp Distribution
- Scalable knowledge base completion with superposition memories
- RMNA: A Neighbor Aggregation-Based Knowledge Graph Representation Learning Model Using Rule Mining
- A Probit Tensor Factorization Model For Relational Learning
- HYPER^2: Hyperbolic Poincare Embedding for Hyper-Relational Link Prediction
- Link Prediction on N-ary Relational Data Based on Relatedness Evaluation
- Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion
- EM-RBR: a reinforced framework for knowledge graph completion from reasoning perspective
- Feature Learning for Meta-Paths in Knowledge Graphs
- Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings
- A Knowledge Enhanced Learning and Semantic Composition Model for Multi-Claim Fact Checking
- Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning
- Technological taxonomies for hypernym and hyponym retrieval in patent texts
- Link Prediction or Perdition: the Seeds of Instability in Knowledge Graph Embeddings
- Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge